Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a clear, sharp, or well-defined quality

    oai_token-act-pair · gpt-3.5-turbo

    words related to clarity and crispness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibu
    -0.71
    hips
    -0.66
    ritch
    -0.63
     Broadway
    -0.63
    ku
    -0.61
     Defender
    -0.60
     shrew
    -0.59
    roit
    -0.59
    lex
    -0.59
     ladder
    -0.58
    POSITIVE LOGITS
    acies
    0.83
     Ridley
    0.81
    meat
    0.78
    acci
    0.77
    keye
    0.74
    vous
    0.73
    mares
    0.73
    assi
    0.72
    eless
    0.70
    zilla
    0.69
    Act Density 0.037%

    No Known Activations